# Orbonomy LLM Extract

> Orbonomy LLM Extract is a paid API for AI agents from main.orbonomy.xyz, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-15).

Extracts structured fields from unstructured text using LLM-based parsing, returning specified fields in a chosen format

## Facts

- Endpoint: POST https://main.orbonomy.xyz/api/llm/extract
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/orbonomy-llm-extract-b5173c36
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_im2EsBCCMtgB-hyRc-Lan

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability orbonomy-llm-extract-b5173c36 -d '<json body>'
```

Example prompt: Extract the name, email, company, and job title from this text as JSON: 'Hi, I'm Sarah Chen, Senior Engineer at DataFlow Inc. You can reach me at sarah.chen@dataflow.io.'

## When to prefer this

Use this endpoint when you need to extract specific named fields from arbitrary unstructured text using LLM intelligence, especially when regex or rule-based parsing would be brittle. Prefer this over generic NLP pipelines when you need flexible field specification at runtime and pay-per-call pricing is acceptable.

## Known failure modes

- Text too long or malformed — may return success: false
- Requested fields not present in text — fields may be empty or null
- Invalid format string — may cause parsing or response error
- Ambiguous field names — LLM may misidentify or conflate fields
- Network or payment failure via x402 protocol — HTTP 402 or timeout

## How this service works

50+ pay-per-call API endpoints across accommodation, AI, content, fact-checking, and data services. Powered by x402 protocol.

## Output

A JSON object with a 'success' boolean and the extracted field values corresponding to the requested fields, parsed from the input text using LLM inference.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text",
  "fields",
  "format"
 ],
 "properties": {
  "text": {
   "type": "string"
  },
  "fields": {
   "type": "array"
  },
  "format": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "success": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/orbonomy-llm-extract-b5173c36/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from main.orbonomy.xyz](https://www.zero.xyz/host/main.orbonomy.xyz/llms.txt)